The classical attribute reduction algorithm is not suitable for the neighborhood decision information system of numerical attribute. Since any feature subset in real feature space can be approximated by neighborhood i...
The classical attribute reduction algorithm is not suitable for the neighborhood decision information system of numerical attribute. Since any feature subset in real feature space can be approximated by neighborhood information particles, the concept of knowledge granularity is extended to neighborhood rough set from the perspective of the granularity computation. In this paper, knowledge granularity, attribute importance and heuristic algorithm based on the granularity of knowledge in neighborhood rough set are studied from the point of view of neighborhood relation matrix. The feasibility of heuristic algorithm is analyzed on UCI data sets. Experiments achieve better classification accuracy and lower attribute reduction results than the existing algorithms.
By considering all the three parameters describing Pythagorean fuzzy set, we introduce a new technique of computing correlation coefficient between Pythagorean fuzzy sets from statistical perspective. The correlation ...
详细信息
By considering all the three parameters describing Pythagorean fuzzy set, we introduce a new technique of computing correlation coefficient between Pythagorean fuzzy sets from statistical perspective. The correlation coefficient value obtain via this technique shows strength of correlation between the Pythagorean fuzzy sets and indicates whether the Pythagorean fuzzy sets under consideration are related negatively or positively in contrast to other existing correlation coefficient approaches in Pythagorean fuzzy context, which only assess the strength of relationship. Certain numerical examples are considered to ascertain the authenticity of this method over similar techniques studied in intuitionistic/Pythagorean fuzzy contexts. Some pattern recognition problems are resolved with the aid of the new technique. For higher productivity sake, this technique could be approached from an object-oriented perspective.
Many recently developed object detectors focused on coarse-to-fine framework which contains several stages that classify and regress proposals from coarse-grain to fine-grain, and obtains more accurate detection gradu...
详细信息
We propose Reduced Collatz Conjecture that is equivalent to Collatz Conjecture, which states that every positive integer can return to an integer less than it, instead of 1. Reduced Collatz Conjecture should be easier...
详细信息
We propose Reduced Collatz conjecture and prove that it is equivalent to Collatz conjecture but more primitive due to reduced dynamics. We study reduced dynamics (that consists of occurred computations from any starti...
详细信息
Video-based person re-identification is an important research area in computer vision. Quality Aware Network(QAN) is a model that is robust to noise in the videos. It calculates the weighted average of all the frames&...
详细信息
Video-based person re-identification is an important research area in computer vision. Quality Aware Network(QAN) is a model that is robust to noise in the videos. It calculates the weighted average of all the frames' image features, with each frame's quality score as the weight, and generates a video feature. However, the QAN has poor ability to distinguish pedestrians with highly similar clothing. To address this problem, we analyze the advantages and shortcomings of Quality Pooling and Max Pooling in theory, and propose the Frame Quality and Max Pooling based Late Feature Fusion Method(QMFF). It aims at enhancing the QAN's ability to distinguish pedestrians with similar clothing. First, use Quality Pooling to get the initial ranking list. Then, for each Query, judge whether the top-N candidates in the ranking list are highly similar in clothing to one another. If the Query meets the similarity criterion, Max Pooling with Frame Quality Filter is used. Local salient features selected by Max Pooling help distinguish pedestrians more accurately. Experimental results on the iLIDS-VID dataset show that the proposed method is superior to the QAN and many recently proposed methods.
We propose Reduced Collatz Conjecture that is equivalent to Collatz Conjecture but is easier to explore, because reduced dynamics is more primitive than original dynamics and presents better structures (e.g., period a...
详细信息
An energy efficient truncated inner product unit is proposed in this paper. The proposed unit is pipelined and processes the m pairs of n-bit operands in serial, so that only one unit is required and it can be reused ...
详细信息
Efficient scheduling algorithms play an essential part in heterogeneous computing systems (HeCS) to achieve high performance. So we proposed a new efficient dynamic multi-strategies scheduling algorithm (DMS). The bas...
详细信息
暂无评论